ML-based radiative transfer parameterization in the ICON climate model (Guillaume Bertoli, ETH Zurich)

26.09.2024 16:15

As climate modellers prepare their code for kilometre-scale global simulations, the computationally demanding radiative transfer parameterization is a prime candidate for machine learning (ML) emulation. This project contributes to the discussion on how to incorporate physical constraints into an ML-based radiative parameterization,

and how different neural network (NN) designs and output normalization affect prediction performance. A random forest is used as a baseline method, with the European Centre for Medium-Range Weather Forecasts (ECMWF) model ecRad, the operational radiation scheme in the Icosahedral Nonhydrostatic Weather and Climate Model (ICON), used for training. For the best emulator, we use a recurrent neural network architecture which closely imitates the physical process it emulates.

We additionally normalize the shortwave and longwave fluxes to reduce their dependence from the solar angle and surface temperature respectively. Finally, we train the model with an additional heating rates penalty in the loss function. Because ICON top height layers are artificial sponge layers, we use an idealized formula to infer the radiation there. We perform a one month ICON simulation with an ML radiation emulator and compare it to a simulation with ecRad. The simulation with the ML solver remains accurate while the computation of the entire simulation is up to 3x faster. The machine learning emulator does not seem to affect the stability of ICON on longer simulations.

Lieu

Conseil Général 7-9, Room 1-15 (unusual room and time!), Séminaire d'analyse numérique

entrée libre